Jaaz is an open source multimodal creative assistant designed to help users generate and organize visual media using artificial intelligence. It functions as a creative workspace where images, videos, and visual storyboards can be produced and arranged on an infinite canvas environment. It combines AI agents with visual editing tools, allowing users to generate media through prompts, sketches, or simple instructions. Jaaz supports multiple AI models and can integrate both local and cloud-based inference systems, enabling flexible creative workflows. Jaaz emphasizes privacy and local-first operation, allowing creators to run AI models locally so that their data does not leave their device. It also includes collaborative planning tools such as visual layouts and storyboard organization to support complex creative projects. By combining generative AI with a canvas-based interface, the project aims to provide a creative platform.
Features
- Infinite canvas workspace for planning layouts, scenes, and visual storyboards
- One-prompt generation of images or videos using integrated AI models
- AI agent that assists with prompt writing and creative media generation
- Support for local AI models through tools such as Ollama and ComfyUI
- Chat-based editing that enables style transfer, object removal, and image edits
- Flexible deployment with options for local, hybrid, or API-based workflows